© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35468
    Prev
    Next
    INDEX
    Explanations

    learn more about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    チコミ
    -1.30
    Ако
    -1.30
    enação
    -1.26
    Other
    -1.26
    トム
    -1.25
     guapos
    -1.23
    ibatkan
    -1.23
    ようですが
    -1.20
    What
    -1.20
     tiende
    -1.19
    POSITIVE LOGITS
     about
    3.09
     of
    2.94
     on
    1.92
     from
    1.67
     how
    1.59
    ांकि
    1.45
     with
    1.43
     milyen
    1.32
     acerca
    1.30
     hogyan
    1.28
    Activations Density 0.007%

    No Known Activations